Also, using stateful GRU to randomize initialization

Krishna Subramani authored 3 years ago and Jean-Marc Valin committed 3 years ago

Making LPC computation and prediction differentiable

Also providing links to suitable training data

Jean-Marc Valin authored 3 years ago and Jean-Marc Valin committed 3 years ago

Down to 20 features

Only on the C side, no sparse GRU B training yet

Weights are the same, but they are dumped to C differently.

Adapted from PR: https://github.com/mozilla/LPCNet/pull/134
by zhuxiaoxu <zhuxiaoxu@ainirobot.com>
but had to be reworked due to previous weight quantization changes.

Makes loading faster

AVX without AVX2 should now work again too.

Avoids having to compute a sigmoid